homework assignment

For this week’s homework assignment, you will be asked to carry out two chi-square tests on survey data.
The first will be a chi-square goodness of fit test to determine if there is a brand preference in a pet food
category. The second will be a chi-square test of independence to test whether a person’s classification as a
promoter or detractor is independent from whether or not they will sign up for an online reward program.
The assignment will consist of the following steps:
1. Create frequency tables from the raw data provided on D2L that will enable you to run your chi-square
test
2. Statement of your null and alternative hypotheses for each assignment
3. Create an R script that will run the two chi square tests
4. Review the results of your tests and determine whether to accept or reject your null hypothesis
5. State your conclusions for each test in the format taught in class.
6. Upload your frequency tables, R script, and statement of conclusions to the D2L page.
Part 1: Chi-square goodness of fit test: Are all brands of dog food used equally?
For part 1 of this assignment, you will be conducting a goodness of fit test on survey data about which brand of
dogfood consumers use most often. Your assignment is to determine whether all brands in the category are
used equally, or if some brands are used more than others. To complete this part of the assignment, you will
use the data set called Homework 2 GOF Data.xls. This data set is located in the homework assignment item
(under the Table of Contents -> Learning Modules -> Week 2 area of D2L).
For this assignment, imagine that you have been asked to prove, based on market research data you have
collected, that there is actually brand differentiation in terms of usage. You have a data set of nearly 400
consumers who took a survey where they answered the question “Which brand of dog food do you use most
often?”
Page 2 of 4
Survey respondents had the following 7 brands to choose from:
• Gravy Train
• Iams
• Kibbles and Bits
• Pedigree
• Purina Alpo
• Purina Beneful
• Purina Dog Chow
While you are fairly certain that brand usage is significantly different among brands, you must provide your
team with statistical evidence to prove this. To make your case, you will carry out a chi-square goodness of fit
test to see whether your data deviate from the equal probabilities across all brands. To carry out your analysis
for this assignment, you must do the following:
1. Create a frequency table that reflects counts for each brand of how many people use that brand most
often. This can be done either in Excel or in R depending on preference.
2. Compute the expected probabilities, given the assumption that all brands have equal probabilities. This
can be done either in Excel or in R depending on preference.
3. Using the submission form UG-MKTG-376-Homework-2-Submission-Form.docx located in the Table of
Contents -> Learning Modules -> Week 2 area of D2L, state the null and alternative hypothesis for the
test you will run.
4. Write the correct R code to calculate the chi-square test.
5. View the results of your test and determine whether or not to reject the null hypothesis.
6. Copy your R script into the submission form. Your script should include at least one line for how you
brought data into R (using the read.csv command) and one line for the test that you ran.
7. Report the chi-square, degrees of freedom, and p-value from the results of your test in the submission
form.
8. State whether or not the null hypothesis can be rejected in the submission form.
9. Save your submission form and your frequency table (with expected probabilities) to be uploaded to
D2L.
Part 2: Chi-square test of independence: Is reward program participation independent of NPS classification
group?
For part 2 of your assignment, you will be asked to identify if reward program participation is independent of
whether individuals are classified as Promoters, Passives, and Detractors in the Net Promoter Score framework.
For this part of the assignment, you will use the Homework 2 Finale NPS.xls data set.
As in the first part of the assignment, you have collected survey data and will use it to address a group-level
question. In this case, you will be asking whether or not Net Promoter groupings have any bearing on whether
or not visitors choose to enroll in a reward program. To answer this question statistically, you will use the Chisquare test of independence. To complete this part of the assignment you will:
1. Create a frequency contingency table that reflects counts of those who did and did not enroll in the
reward program for each of three groups: promoters, passives, and detractors. Remember that for the
test of independence you must create your table in R using the table function. You will want your table
to have NPS groups as rows and Reward Classification groups as columns.
2. Continuing to use the submission form UG-MKTG-376-Homework-2-Submission-Form.docx located in
the Table of Contents -> Learning Modules -> Week 2 area of D2L, state the null and alternative
hypothesis for the test you will run.
3. Write the correct R code to calculate the chi-square test.
4. View the results of your test and determine whether or not to reject the null hypothesis.